COVID-19 Detection Using Slices Processing Techniques and a Modified Xception Classifier from Computed Tomography Images

The unprecedented global challenge posed by the COVID-19 pandemic has underscored the critical need for advanced diagnostic methodologies to effectively curb the virus's spread. Among these methodologies, Computed Tomography (CT) imaging has emerged as a vital tool in providing detailed insights into the manifestations of the disease. In this context, the utilization of CT scan images has proven instrumental in detecting the presence of the virus and understanding its impact on the respiratory system. The intricate details captured by CT scans offer a comprehensive view of the pulmonary structures, making them invaluable for early and accurate diagnosis [1]. To address the urgency of timely and precise COVID-19 diagnosis, the integration of advanced computational techniques has become imperative. Deep learning, particularly through the lens of transfer learning, has demonstrated remarkable potential in enhancing diagnostic accuracy and efficiency.